How to use

org.apache.tika.parser.pdf.PDFParser

constructor

 public class PDFReader{
  public static void main(String args[]) {
    PDFTextStripper pdfStripper = null;
    PDDocument pdDoc = null;
    COSDocument cosDoc = null;
    File file = new File("C:/my.pdf");
    try {
      PDFParser parser = new PDFParser(new FileInputStream(file));
      parser.parse();
      cosDoc = parser.getDocument();
      pdfStripper = new PDFTextStripper();
      pdDoc = new PDDocument(cosDoc);
      pdfStripper.setStartPage(1);
      pdfStripper.setEndPage(5);
      String parsedText = pdfStripper.getText(pdDoc);
      System.out.println(parsedText);
    } catch (IOException e) {
      // TODO Auto-generated catch block
      e.printStackTrace();
    } 
  }
}

public static Metadata getMet(URL url) throws IOException, SAXException,
    TikaException {
  Metadata met = new Metadata();
  PDFParser parser = new PDFParser();
  parser.parse(url.openStream(), new BodyContentHandler(), met, new ParseContext());
  return met;
}

 public void parse(InputStream stream, ContentHandler handler,
   Metadata metadata, ParseContext context) throws IOException,
   SAXException, TikaException {
  TikaInputStream tis = TikaInputStream.get(stream, new TemporaryResources());
  File tmpFile = tis.getFile();

  GrobidRESTParser grobidParser = new GrobidRESTParser();
  grobidParser.parse(tmpFile.getAbsolutePath(), handler, metadata, context);

  PDFParser parser = new PDFParser();
  parser.parse(new FileInputStream(tmpFile), handler, metadata, context);
 }
}

File file = new File(fileName);
try {
  parser = new PDFParser(new FileInputStream(file));
  parser.parse();
  cosDoc = parser.getDocument();

private static void initParser(Fs fs) {
  if (parser == null) {
    PDFParser pdfParser = new PDFParser();
    DefaultParser defaultParser;
    if (fs.isPdfOcr()) {
      logger.debug("OCR is activated for PDF documents");
      if (ExternalParser.check("tesseract")) {
        pdfParser.setOcrStrategy("ocr_and_text");
      } else {
        logger.debug("But Tesseract is not installed so we won't run OCR.");
      }
      defaultParser = new DefaultParser();
    } else {
      logger.debug("OCR is disabled. Even though it's detected, it must be disabled explicitly");
      defaultParser = new DefaultParser(
          MediaTypeRegistry.getDefaultRegistry(),
          new ServiceLoader(),
          Collections.singletonList(TesseractOCRParser.class));
    }
    Parser PARSERS[] = new Parser[2];
    PARSERS[0] = defaultParser;
    PARSERS[1] = pdfParser;
    parser = new AutoDetectParser(PARSERS);
  }
}

 var PDFParser = require('pdf2json');
var pdfParser = new PDFParser();

pdfParser.on('pdfParser_dataReady', function(data) {
  var doc = data.PDFJS && data.PDFJS.pdfDocument && data.PDFJS.pdfDocument.numPages;
  console.log('Number of pages:', doc);
});
// pdfParser.on('pdfParser_dataError', _.bind(_onPFBinDataError, self));

pdfParser.loadPDF('test.pdf');

  @Override
  protected Parser getParser() 
  {
    return new PDFParser();
  }
}

  @Override
  protected Parser getParser() 
  {
    return new PDFParser();
  }
}

 var fs = require("fs");

// https://github.com/modesty/pdf2json
var PDFParser = require("./node_modules/pdf2json/PDFParser");
var pdfParser = new PDFParser(this,1);

pdfParser.on("pdfParser_dataError", errData => console.error(errData.parserError));
pdfParser.on("pdfParser_dataReady", pdfData => {
  console.log(pdfParser)
  fs.writeFile("./content.txt", pdfParser.getRawTextContent());
});

  /**
   * @see org.opencms.search.extractors.I_CmsTextExtractor#extractText(java.io.InputStream, java.lang.String)
   */
  @Override
  public I_CmsExtractionResult extractText(InputStream in) throws Exception {

    return extractText(in, new PDFParser());
  }
}

public void ReadPDF() throws Exception {
 URL TestURL = new URL("http://www.axmag.com/download/pdfurl-guide.pdf");
 BufferedInputStream TestFile = new BufferedInputStream(TestURL.openStream());
 PDFParser TestPDF = new PDFParser(TestFile);
 TestPDF.parse();
 String TestText = new PDFTextStripper().getText(TestPDF.getPDDocument());
 Assert.assertTrue(TestText.contains("Open the setting.xml, you can see it is like this"));
 }

private PdfParser() {
  Map<Pattern, MediaType> patterns = new HashMap<Pattern, MediaType>();
  patterns.put(Pattern.compile(".*\\.pdf", Pattern.CASE_INSENSITIVE),
      MediaType.application("pdf"));
  NameDetector detector = new NameDetector(patterns);
  tika = TikaFactory.newTika(detector, new PDFParser());
}

InputStream input = new FileInputStream("sample.pdf");
   ContentHandler handler = new BodyContentHandler(Integer.MAX_VALUE);
   Metadata metadata = new Metadata();
   new PDFParser().parse(input, handler, metadata, new ParseContext());
   String plainText = handler.toString();
   System.out.println(plainText);

 File in = new File("somefile.pdf");
InputStream fin = new FileInputStream(in);
PDFParser parser = new PDFParser(fin);
parser.setTempDirectory(new File(tempDirectoryPath));
parser.parse();
PDDocument document = parser.getPDDocument();

 InputStream input = new FileInputStream(new File(resourceLocation));
ContentHandler textHandler = new BodyContentHandler();
Metadata metadata = new Metadata();
PDFParser parser = new PDFParser();
parser.parse(input, textHandler, metadata);
input.close();
out.println("Title: " + metadata.get("title"));
out.println("Author: " + metadata.get("Author"));
out.println("content: " + textHandler.toString());

 InputStream input = new FileInputStream(new File(resourceLocation));
ContentHandler textHandler = new BodyContentHandler();
Metadata metadata = new Metadata();
PDFParser parser = new PDFParser();
parser.parse(input, textHandler, metadata);
input.close();
out.println("Title: " + metadata.get("title"));
out.println("Author: " + metadata.get("Author"));
out.println("content: " + textHandler.toString());

private void openPDFDoc(final File pdfFile) throws Exception {
   File originalPDF = pdfFile;
   PDFParser parser = new PDFParser(new BufferedInputStream(new FileInputStream(
       originalPDF)));
   parser.parse();
   PDDocument originialPdfDoc = parser.getPDDocument();
   boolean isOriginalDocEncrypted = originialPdfDoc.isEncrypted();
   if (isOriginalDocEncrypted) {
     originialPdfDoc.openProtection(new StandardDecryptionMaterial("password"));
   }
 }

 public void parse(InputStream stream, ContentHandler handler,
   Metadata metadata, ParseContext context) throws IOException,
   SAXException, TikaException {
  TikaInputStream tis = TikaInputStream.get(stream, new TemporaryResources());
  File tmpFile = tis.getFile();

  GrobidRESTParser grobidParser = new GrobidRESTParser();
  grobidParser.parse(tmpFile.getAbsolutePath(), handler, metadata, context);

  PDFParser parser = new PDFParser();
  parser.parse(new FileInputStream(tmpFile), handler, metadata, context);
 }
}

 public void parse(InputStream stream, ContentHandler handler,
   Metadata metadata, ParseContext context) throws IOException,
   SAXException, TikaException {
  TikaInputStream tis = TikaInputStream.get(stream, new TemporaryResources());
  File tmpFile = tis.getFile();

  GrobidRESTParser grobidParser = new GrobidRESTParser();
  grobidParser.parse(tmpFile.getAbsolutePath(), handler, metadata, context);

  PDFParser parser = new PDFParser();
  parser.parse(new FileInputStream(tmpFile), handler, metadata, context);
 }
}

 PDFParser pdfParser = new PDFParser(new FileInputStream("c:\\temp\\owgr49f2013.pdf"));
pdfParser.parse();
PDDocument pdDocument = pdfParser.getPDDocument();

PDFTextStripper stripper = new PDFTextStripper("UTF-8");
stripper.setSortByPosition(false);
stripper.setWordSeparator("###");
System.out.println(stripper.getText(pdDocument));